Browse OpenForge documentation
Siqoq · OSS Project

Siqoq

A Physical AI infrastructure experiment that preserves semantic event and action contracts from simulation to edge hardware

Physical AIEdge AISimulationONNX RuntimeRoboticsOpenTelemetry
RepositoryGitHub ↗
Documentation3 sections
Updated2026-09-14T00:00:00.000Z
ECOSYSTEM ROLE
Physical AI Infrastructure

Validates adapter-oriented Physical AI infrastructure that preserves semantic event and action contracts from simulation to real edge hardware.

Simulation-firstSemantic eventsSafety-gated actions
PROJECT CONFORMANCE

Repository evidence checklist

2 present · 7 missing

Present means an explicit repository or site artifact was observed. Missing means this audit did not observe that artifact; it does not prove the underlying practice does not exist. Tracked links point to the closest existing backlog owner and do not create issues automatically.

CONTRIBUTING
Missing
CODE_OF_CONDUCT
Missing
SECURITY.md
Missing
SBOM evidence
Missing
Provenance / attestation
Missing
GitHub Release
Missing
Project detail docs
Present
3 sections
Evidence observed
Community contributor signal
Present
2 contributors
Evidence observed
repository audit not indexed
Problem

Perception-to-action workflows become difficult to reuse and verify when simulators, laptops, sensors, and actuators expose unrelated APIs and runtime assumptions

Approach

Separate sensor, inference, transport, policy, and action implementations behind adapters while keeping semantic event and action contracts stable

ENGINEERING EVIDENCE

Show reviewable engineering evidence instead of relying on headline numbers.

Maturity
Bootstrap

Separates the current Python/CLI/event-model core from target architecture claims.

Stable boundary
Event / Action

Keeps semantic events and validated actions stable while runtimes and devices change.

Runtime path
CPU first

Establishes an OpenCV/ONNX Runtime baseline before accelerator-specific paths.

Safety
Adapter gated

Separates policy decisions, safety validation, and hardware actuation.

START HERE

You do not need to read the README from top to bottom.

ENGINEERING PRINCIPLES
Source-driven

Keep project explanations grounded in repository source, architecture, tests, releases, and operating records.

Independently useful

Even inside one ecosystem, keep boundaries independently installable, verifiable, and releasable whenever possible.

Evidence over claims

Prefer reproducible verification, incident knowledge, upgrade gates, and operating evidence over feature-count claims.

Project introduction

Siqoq validates the infrastructure contracts that must survive the move from simulation to real edge systems before attempting to build a complete Physical AI product.

Raw frames and device SDKs do not become the platform API. Downstream systems consume semantic events such as object.detected, while actions pass through explicit policy and safety checks before an adapter reaches hardware.

Current implementation boundary

Siqoq is currently an early bootstrap / architecture validation project.

  • Python package and CLI foundation
  • semantic event model
  • unit-test and CI foundation
  • simulation-first architecture, principles, and roadmap

Isaac Sim/Gazebo integration, real sensor adapters, TensorRT/Jetson acceleration, NATS/MQTT, a ROS 2 bridge, actuator control, and fleet GitOps remain planned work.

Reading path

GoalDocument
Product boundary and current statusOverview
Stable contracts and adapter structureArchitecture
Executable development and verification scopeDevelopment